Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gment
    -0.08
    navigation
    -0.07
     Γεω
    -0.07
    packet
    -0.06
     processes
    -0.06
     inadequate
    -0.06
    Cold
    -0.06
     менее
    -0.06
    十分
    -0.06
     clothing
    -0.06
    POSITIVE LOGITS
    ",(
    0.07
    DM
    0.07
     kod
    0.07
    -Ch
    0.07
    浦
    0.06
     XP
    0.06
     vont
    0.06
    ****↵
    0.06
    �
    0.06
     dahil
    0.06
    Act Density 0.030%

    No Known Activations